Event data from a Dutch province’s intersections was used to build a set of deep learning models able to predict real-time and future queue lengths at each red light. These predictions can be used to adjust traffic light priorities and durations, and to inform drivers.

Data from induction loops, local weather, historical ticketing and calendar data, were used to build operational traffic intensity models to predict traffic at toll plazas. Sharing forecasts with drivers allows them to make departure time changes and avoid congestion.

Using data from sensors, reported alarms, maintenance and failure logs, HAL24K created sensor network models to predict the time and location of equipment failure in water treatment plants.

Accurate predictions of water levels enable water authorities to be more effective in taking measures, decreasing risk and optimizing energy consumption for their management areas.

With predictions of shared bike movements, operators can easily identify how to increase yield with fewer bikes, as well as how to predict availability of the cycles at docks and so improve user satisfaction.

HAL24K’s data intelligence solution predicts the weekly number of replacement vehicles needed per hub and boosts efficiencies for roadside assistance provider.